Real-world Entities Research Articles

PromptEM

Entity Matching (EM), which aims to identify whether two entity records from two relational tables refer to the same real-world entity, is one of the fundamental problems in data management. Traditional EM assumes that two tables are homogeneous with the aligned schema, while it is common that entity records of different formats (e.g., relational, semi-structured, or textual types) involve in practical scenarios. It is not practical to unify their schemas due to the different formats. To support EM on format-different entity records, Generalized Entity Matching (GEM) has been proposed and gained much attention recently. To do GEM, existing methods typically perform in a supervised learning way, which relies on a large amount of high-quality labeled examples. However, the labeling process is extremely labor-intensive, and frustrates the use of GEM. Low-resource GEM, i.e., GEM that only requires a small number of labeled examples, becomes an urgent need. To this end, this paper, for the first time, focuses on the low-resource GEM and proposes a novel low-resource GEM method, termed as PromptEM. PromptEM has addressed three challenging issues (i.e., designing GEM-specific prompt-tuning, improving pseudo-labels quality, and running efficient self-training) in low-resource GEM. Extensive experimental results on eight real benchmarks demonstrate the superiority of PromptEM in terms of effectiveness and efficiency.

Entity-oriented spatial coding scheme and its application for spatial topology

ABSTRACT Based on a newly proposed spatial data model Spatial Chromatic Model (SCM), we developed a spatial coding scheme, called the full-coded Ordinary Arranged Chromatic Diagram (full-OACD). As a type of spatial tessellation, full-OACD partitions a geographic space into a number of subspaces, such as cells, edges, and vertices. These subspaces are called spatial particles and are assigned with unique codes chromatic codes. The generation, structure, computation, and properties of full-OACD are introduced. Relations between particulate chromatic codes and spatial topology are investigated. Full-OACD is a kind of new discrete spatial coordinate system where the information of real-world entities is embedded. Full-OACD provides an informative and meaningful spatial coding framework for spatial topological analysis and many other potential applications in geospatial information science.

SEMANTIC QUERYING IN EARTH OBSERVATION DATA CUBES

Abstract. Earth observation (EO) data cubes have revolutionized the way large volumes of EO data can be stored, accessed, and processed. However, users coming from application domains outside of traditional EO research still face some significant technical barriers when querying an EO data cube with the aim to infer knew knowledge about real world entities and events. They have to interpret EO data in order to give them meaning, which is an ill-posed problem that requires advanced expertise in the field of EO analytics. We propose a semantic querying framework in which users query the EO data cube through an ontology, rather than accessing the data values themselves. The ontology formalizes symbolic representations of real-world entities and events, which are mapped to data values in the EO data cube through a mapping component formulated by an EO expert. This takes away the need for users to be aware of the EO data and how to interpret them, and therefore lowers the technical barriers to extract valuable information from EO data. We implemented a proof-of-concept of our approach as an open-source Python package.

Frost

"Bad" data has a direct impact on 88% of companies, with the average company losing 12% of its revenue due to it. Duplicates - multiple but different representations of the same real-world entities - are among the main reasons for poor data quality, so finding and configuring the right deduplication solution is essential. Existing data matching benchmarks focus on the quality of matching results and neglect other important factors, such as business requirements. Additionally, they often do not support the exploration of data matching results. To address this gap between the mere counting of record pairs vs. a comprehensive means to evaluate data matching solutions, we present the Frost platform. It combines existing benchmarks, established quality metrics, cost and effort metrics, and exploration techniques, making it the first platform to allow systematic exploration to understand matching results. Frost is implemented and published in the open-source application Snowman, which includes the visual exploration of matching results, as shown in Figure 1.

DADER

Entity resolution (ER) is a core data integration problem that identifies pairs of data instances referring to the same real-world entities, and the state-of-the-art results of ER are achieved by deep learning (DL) based approaches. However, DL-based approaches typically require a large amount of labeled training data (i.e. , matching and non-matching pairs), which incurs substantial manual labeling efforts. In this paper, we introduce DADER , a hands-off deep ER system through domain adaptation. DADER utilizes multiple well-labeled source ER datasets to train a DL-based ER model for a new target ER dataset that does not have any labels or with only a few labels. To address the key challenge of domain shift, DADER judiciously selects labeled entity pairs from the source and then aligns distributions of the source and the target by using six popular domain adaptation strategies. DADER can also harness the users to gather a few labels for further improvement. We have built DADER as an open-sourced Python Library with intuitive APIs and demonstrated its utility on supporting hands-off ER in real-world scenarios.

CERTEM

Entity resolution (ER) aims at identifying record pairs that refer to the same real-world entity. Recent works have focused on deep learning (DL) techniques, to solve this problem. While such works have brought tremendous enhancements in terms of effectiveness in solving the ER problem, understanding their matching predictions is still a challenge, because of the intrinsic opaqueness of DL based solutions. Interpreting and trusting the predictions made by ER systems is crucial for humans in order to employ such methods in decision making pipelines. We demonstrate CERTEM an explanation system for ER based on CERTA, a recently introduced explainability framework for ER, that is able to provide both saliency explanations, which associate each attribute with a saliency score, and counterfactual explanations, which provide examples of values that can flip a prediction. In this demonstration we will showcase how CERTEM can be effectively employed to better understand and debug the behavior of state-of-the-art DL based ER systems on data from publicly available ER benchmarks.

Taxonomy of Attacks on Privacy-Preserving Record Linkage

Record linkage is the process of identifying records that corresponds to the same real-world entities across different databases. Due to the absence of unique entity identifiers, record linkage is often based on quasi-identifying values of entities (individuals) such as their names and addresses. However, regulatory ethical and legal obligations can limit the use of such personal information in the linkage process in order to protect the privacy and confidentiality of entities. Privacy-preserving record linkage (PPRL) aims to develop techniques that enable the linkage of records without revealing any sensitive or confidential information about the entities that are represented by these records. Over the past two decades various PPRL techniques have been proposed to securely link records between different databases by encrypting and/or encoding sensitive values. However, some PPRL techniques, such as popular Bloom filter encoding, have shown to be susceptible to privacy attacks. These attacks exploit the weaknesses of PPRL techniques by trying to reidentify encrypted and/or encoded sensitive values. In this paper we propose a taxonomy for analysing such attacks on PPRL where we categorise attacks across twelve dimensions, including different types of adversaries, different attack types, assumed knowledge of the adversary, the vulnerabilities of encoded and/or encrypted values exploited by an attack, and assessing the success of attacks. Our taxonomy can be used by data custodians to analyse the privacy risks associated with different PPRL techniques in terms of existing as well as potential future attacks on PPRL.

Knowledge Graph Entity Alignment Using Relation Structural Similarity

Embedding-based entity alignment, which represents knowledge graphs as low-dimensional embeddings and finds entities in different knowledge graphs that semantically represent the same real-world entity by measuring the similarities between entity embeddings, has achieved promising results. However, existing methods are still challenged by the error accumulation of embeddings along multi-step paths and the semantic information loss. This paper proposes a novel embedding-based entity alignment method that iteratively aligns both entities and relations with high similarities as training data. Newly-aligned entities and relations are used to calibrate the corresponding embeddings in the unified embedding space, which reduces the error accumulation. To reduce the negative impact of semantic information loss, the authors propose to use relation structural similarity instead of embedding similarity to align relations. Experimental results on five widely used real-world datasets show that the proposed method significantly outperforms several state-of-the-art methods for entity alignment.

From social contingency to verbal reference: A constructivist hypothesis.

In the first year of life, infants' word learning is slow, laborious, and requires repeated exposure to word-referent co-occurrences. In contrast, by 14-18 months, infants learn words from just a few labeling events, use joint attention and eye gaze to decipher word meaning, and begin to use speech to communicate about absent things. We propose that this remarkable advancement in word learning results from attaining a referential understanding of words-that words are linked to mental representations and used intentionally to communicate about real-world entities. We suggest that verbal reference is supported by codeveloping conceptual, social, representational, and statistical learning capacities. We also propose that infants' recognition of this tri-directional link between words, referents, and mental representations is enabled by their experience participating in and observing socially contingent interactions. Understanding verbal reference signals a qualitative shift in infants' word learning. This shift enables infants to bootstrap word meanings from syntax and semantics, learn novel words and facts from nonostensive communication, and make inferences about speakers' epistemic competence based on their language production. In this paper, we review empirical findings across multiple facets of infant cognition and propose a novel developmental theory of verbal reference. Finally, we suggest new directions of empirical research that may provide stronger and more direct evidence for our theory and contribute to our understanding of the development of verbal reference and language-mediated learning in infancy and beyond. (PsycInfo Database Record (c) 2022 APA, all rights reserved).

Trusting Digital Twins

A digital twin is a virtual representation of real-world entities and processes synchronized at a specified frequency and fidelity. This new technology has the same trust concerns as do other systems, and we explore them here.

A Graph-Cut-Based Approach to Community Detection in Networks

Networks can be used to model various aspects of our lives as well as relations among many real-world entities and objects. To detect a community structure in a network can enhance our understanding of the characteristics, properties, and inner workings of the network. Therefore, there has been significant research on detecting and evaluating community structures in networks. Many fields, including social sciences, biology, engineering, computer science, and applied mathematics, have developed various methods for analyzing and detecting community structures in networks. In this paper, a new community detection algorithm, which repeats the process of dividing a community into two smaller communities by finding a minimum cut, is proposed. The proposed algorithm is applied to some example network data and shows fairly good community detection results with comparable modularity Q values.

Context-Based Emotion Predictor: A Decision- Making Framework for Mobile Data

The proliferation of big data for web-enabled technologies allows users to publish their views, suggestions, sentiments, emotions, and opinionative content about several real-world entities. These available opinionative texts have greater importance to those who are inquisitive about their desired entities, but it becomes an arduous task to capture such a massive volume of user-generated content. Emotions are an inseparable part of communication, which is articulated in multiple ways and can be used for making better decisions to reshape business strategies. Emotion detection is a subdiscipline at the crossroads of text mining and information retrieval. Context is a common phenomenon in emotions and is inherently hard to capture not only for the machine but even for a human. This study proposes a decision-making framework for efficient emotion detection of mobile reviews. An unsupervised lexicon-based algorithm has been developed to tackle the problem of emotion prediction. Dictionaries and corpora are used as backend resources in the semantic orientation of emotion words, whereas the major contribution is to cope with contextualized emotion detection. The proposed framework outperformed the existing emotion detection systems by achieving 86% accuracy over mobile reviews.

JointMatcher: Numerically-aware entity matching using pre-trained language models with attention concentration

Entity matching (EM) aims to identify whether two records refer to the same underlying real-world entity. Traditional entity matching methods mainly focus on structured data, where the attribute values are short and atomic. Recently, there has been an increasing demand for matching textual records, such as matching descriptions of products that correspond to long spans of text, which challenges the applications of these methods. Although a few deep learning (DL) solutions have been proposed, these solutions tend to “directly” use the DL techniques and treat the EM as NLP tasks without determining the unique demand for the EM task. Thus, the performance of these DL-based solutions is still far from satisfactory. In this paper, we present JointMatcher, a novel EM method based on the pre-trained Transformer-based language models so that the generated features of the textual records contain the context information. We realize that more attention paid to the similar segments and number-contained segments of the record pair is crucial for accurate matching. To integrate the high-contextualized features with the consideration of paying more attention to the similar segments and the number-contained segments, JointMatcher is equipped with the relevance-aware encoder and the numerically-aware encoder. Extensive experiments using structured and real-world textual datasets demonstrated that JointMatcher outperforms the previous state-of-the-art (SOTA) results without injecting any domain knowledge when small or medium size training sets are used.

Linked Data Fusion Based on Similarity Calculation and K-Nearest Neighbor

The development of semantic web technology supports the continuous development of linked data and its applications. In order to make effective use of the growing linked data on the web, multi-source data should be fused, which is a key step in multi-source large-scale data analysis and management. Currently, merging these data can be difficult, because various sources usually provide multiple conflict descriptions for entities in the same real world. To complete the fusion, we need to solve the problem of object conflict. This paper proposes a linked data fusion method based on similarity calculation and k-nearest neighbor. This method has two contributions. Firstly, a similarity calculation method of linked data is proposed, which can effectively integrate URI nodes and blank nodes in linked data; Secondly, a literal type node fusion strategy based on k-nearest neighbor classification method is proposed, which realizes the automation of fusion and has the independence of data source. The results show that compared with other methods, this method can improve the conciseness and consistency and precision by up to 12.9%, 30.6% and 12%.

Automating Duplicate Detection for Lexical Heterogeneous Web Databases

Introduction: The need for efficient search engines has been identified with the everincreasing technological advancement and huge growing demand for data on the web. Method: Automating duplicate detection over a query results in identifying the records from multiple web databases that point to a similar real-world entity and return non-matching records to the end-users. The proposed algorithm in this paper is based on an unsupervised approach with classifiers over heterogeneous web databases that return more accurate results with high precision, Fmeasure, and recall. Different assessments have also been executed to analyze the efficacy of the proposed algorithm for the identification of duplicates. Result: Results show that the proposed algorithm has greater precision, F-score measure, and the same recall values as compared to standard UDD. Conclusion: This paper aims to introduce an algorithm that automates the process of duplicate detection for lexical heterogeneous web databases. Discussion: This paper concludes that the proposed algorithm outperforms the standard UDD.

EXP-Crowd: A Gamified Crowdsourcing Framework for Explainability.

The spread of AI and black-box machine learning models made it necessary to explain their behavior. Consequently, the research field of Explainable AI was born. The main objective of an Explainable AI system is to be understood by a human as the final beneficiary of the model. In our research, we frame the explainability problem from the crowds point of view and engage both users and AI researchers through a gamified crowdsourcing framework. We research whether it's possible to improve the crowds understanding of black-box models and the quality of the crowdsourced content by engaging users in a set of gamified activities through a gamified crowdsourcing framework named EXP-Crowd. While users engage in such activities, AI researchers organize and share AI- and explainability-related knowledge to educate users. We present the preliminary design of a game with a purpose (G.W.A.P.) to collect features describing real-world entities which can be used for explainability purposes. Future works will concretise and improve the current design of the framework to cover specific explainability-related needs.

Analyzing how BERT performs entity matching

State-of-the-art Entity Matching (EM) approaches rely on transformer architectures, such as BERT , for generating highly contex-tualized embeddings of terms. The embeddings are then used to predict whether pairs of entity descriptions refer to the same real-world entity. BERT-based EM models demonstrated to be effective, but act as black-boxes for the users, who have limited insight into the motivations behind their decisions. In this paper, we perform a multi-facet analysis of the components of pre-trained and fine-tuned BERT architectures applied to an EM task. The main findings resulting from our extensive experimental evaluation are (1) the fine-tuning process applied to the EM task mainly modifies the last layers of the BERT components, but in a different way on tokens belonging to descriptions of matching / non-matching entities; (2) the special structure of the EM datasets, where records are pairs of entity descriptions is recognized by BERT; (3) the pair-wise semantic similarity of tokens is not a key knowledge exploited by BERT-based EM models.

Federated learning enabled digital twins for smart cities: Concepts, recent advances, and future directions

Recent advances in Artificial Intelligence (AI) and the Internet of Things (IoT) have facilitated continuous improvement in smart city based applications such as smart healthcare, transportation, and environmental management. Digital Twin (DT) is an AI-based virtual replica of the real-world physical entity. DTs have been successfully adopted in manufacturing and industrial sectors, they are however still at the early stage in smart city based applications. The major reason for this lag is the lack of trust and privacy issues in sharing sensitive data. Federated Learning (FL) is a technology that could be integrated along with DT to ensure privacy preservation and trustworthiness. This paper focuses on the integration of these two promising technologies for adoption in real-time and life-critical scenarios, as well as for ease of governance in smart city based applications. We present an extensive survey on the various smart city based applications of FL models in DTs. Based on the study, some prominent challenges and future directions are presented for better FL–DT integration in future applications. • We present a comprehensive survey on the integration of Federated Learning with Digital Twin. • Discusses recent smart city applications where Federated Learning is integrated with Digital Twin. • Various challenges that still persist and scope for future researchers are highlighted.

Entity resolution on-demand

Entity Resolution (ER) aims to identify and merge records that refer to the same real-world entity. ER is typically employed as an expensive cleaning step on the entire data before consuming it. Yet, determining which entities are useful once cleaned depends solely on the user's application, which may need only a fraction of them. For instance, when dealing with Web data, we would like to be able to filter the entities of interest gathered from multiple sources without cleaning the entire, continuously-growing data. Similarly, when querying data lakes, we want to transform data on-demand and return the results in a timely manner---a fundamental requirement of ELT ( Extract-Load-Transform ) pipelines. We propose BrewER , a framework to evaluate SQL SP queries on dirty data while progressively returning results as if they were issued on cleaned data. BrewER tries to focus the cleaning effort on one entity at a time, following an ORDER BY predicate. Thus, it inherently supports top-k and stop-and-resume execution. For a wide range of applications, a significant amount of resources can be saved. We exhaustively evaluate and show the efficacy of BrewER on four real-world datasets.

Toward Autonomic, Software-Intensive Digital Twin Systems

Digital twins (DTs) mirror and model the characteristics and properties of dynamic, real-world entities known as real twins (RTs). Ensuring the delivery of consistent and reliable RT insights over time demands DTs preserve the correspondence with their counterparts, notwithstanding change.